A5100737919- Topic Modeling
- Advanced Text Analysis Techniques
- Sentiment Analysis and Opinion Mining
- Natural Language Processing Techniques
- Video Surveillance and Tracking Methods
- Advanced Malware Detection Techniques
- Text and Document Classification Technologies
- Anomaly Detection Techniques and Applications
- Adversarial Robustness in Machine Learning
- Network Security and Intrusion Detection
- Industrial Vision Systems and Defect Detection
- Advanced Technologies in Various Fields
- Water Quality Monitoring Technologies
- Maritime Navigation and Safety
- Reinforcement Learning in Robotics
- Smart Agriculture and AI
- Leaf Properties and Growth Measurement
- Advanced Data Storage Technologies
- Bacillus and Francisella bacterial research
- Advanced Measurement and Detection Methods
- Impact of Light on Environment and Health
- Digital Media and Visual Art
- Advanced Image and Video Retrieval Techniques
- Educational Technology and Assessment
- Computational and Text Analysis Methods
Hainan University
2025
Shandong University
2025
Capital Medical University
2024
Southwest University of Science and Technology
2011-2023
Xidian University
2018-2023
Nanjing University of Posts and Telecommunications
2017-2022
Wuhan University
2021
Universidad de Huelva
2020
Southeast University
2016-2017
University of Science and Technology Beijing
2013
Document-level relation extraction aims to detect the relations within one document, which is challenging since it requires complex reasoning using mentions, entities, local and global contexts.Few previous studies have distinguished explicitly, may be problematic because they play different roles in intra-and inter-sentence relations.Moreover, interactions between contexts should considered could help based on our observation.In this paper, we propose a novel mention-based (MRN) module...
The development of sequence-based deep learning methods has greatly increased our understanding how sequence determines function. In parallel, numerous interpretable algorithms have been developed to address complex tasks, such as elucidating regulatory syntax and analyzing non-coding variants from trained models. However, few studies systematically compared evaluated the performance interpretability these algorithms. Here, we introduce a comprehensive benchmark framework for evaluating...
A variety of diseased leaves and background noise types are present in images tomatoes captured real-world environments. However, existing tomato leaf disease recognition models limited to recognizing only a single leaf, rendering them unsuitable for practical applications scenarios. Additionally, these consume significant hardware resources, making their implementation challenging agricultural production promotion. To address issues, this study proposes framework that integrates detection...
Throughout the past decade, vehicular networks have attracted a great deal of interest in various fields. The increasing number vehicles has led to challenges traffic regulation. Vehicle-type detection is an important research topic that found applications numerous Its main purpose extract different features from videos or pictures captured by surveillance so as identify types vehicles, and then provide reference information for monitoring control. In this paper, we propose step-forward...
In recent years, with the development of Internet Things (IoT) technology, a large amount data can be captured from sensors for real-time analysis. By monitoring traffic video IoT, we detect anomalies that may occur and evaluate security. However, number is extremely limited, so there severe over-fitting problem when using traditional deep learning methods. order to solve above, propose similarity metric Convolutional Neural Network (CNN) based on channel attention model anomaly detection...
Due to the powerful ability of data fitting, deep neural networks have been applied in a wide range applications many key areas. However, recent years, it was found that some adversarial samples easily fool networks. These input are generated by adding few small perturbations based on original sample, making very significant influence decision target model case not being perceived. Image segmentation is one most important technologies medical image and automatic driving field. This paper...
As more and multilingual knowledge becomes available on the Web, sharing across languages has become an important task to benefit many applications. One of most crucial kinds Web is taxonomy, which used organize classify data. To facilitate languages, we need deal with problem cross-lingual taxonomy alignment, discovers relevant category in target one language for each source another language. Current approaches aligning taxonomies strongly rely domain-specific information features based...
In recent years, with the development of marine industry, ship navigation environment has become more complicated. Some artificial intelligence technologies, such as computer vision, can recognize, track and count sailing ships to ensure maritime security facilitate management for Smart Ocean systems. Aiming at scaling problem boundary effect traditional correlation filtering methods, we propose a self-selective method based on box regression (BRCF). The proposed mainly includes: (1) A model...
Topic models have been widely applied in discovering topics that underly a collection of documents. Incorporating human knowledge can guide conventional topic to produce which are easily interpreted and semantically coherent. Several kn
Vehicle tracking task plays an important role on the Internet of vehicles and intelligent transportation system. Beyond traditional Global Positioning System sensor, image sensor can capture different kinds vehicles, analyze their driving situation, interact with them. Aiming at problem that convolutional neural network is vulnerable to background interference, this article proposes vehicle method based human attention mechanism for self-selection deep features inter-channel fully connected...
Sentiment analysis in various languages has been a hot research topic with several applications. Most of the existing models have reported to work well widely used language. Were lass directly applying these poor-quality corpora often leads low results. Thus, deal shortcoming we propose cross-lingual sentiment model evolution over time (CLSTOT) which jointly and sentiment. In CLSTOT, consider mapping between sentiment-aware topics under different cultures analyze their time. The...
Superposed constellation technology has received increasing attention due to its robustness the correlation of multiple-input multiple-output (MIMO) channels in visible-light communication (VLC) systems. In this study, a novel superposed three-dimensional 32-quadrature amplitude modulation (3D-32QAM) scheme combined with probabilistic shaping is proposed for MIMO VLC Tetrahedron-shaped 3D-4QAM and cube-shaped 3D-8QAM signals are transmitted from two separate LEDs, which at receiver obtain...
A dissertation is a research report or scientific paper written by an author to obtain certain degree. It reflects postgraduates' achievements and the educational quality of institute, even country. To construct optimized evaluation system for postgraduate (QESPD), we summarized influencing factors invited 10 experienced specialists rate prioritize them based on fuzzy analytic hierarchy process. Four primary indicators (innovation, integrity, scientificity normativity) 16 sub-indicators were...
We consider off-dynamics reinforcement learning (RL) where one needs to transfer policies across different domains with dynamics mismatch. Despite the focus on developing dynamics-aware algorithms, this field is hindered due lack of a standard benchmark. To bridge gap, we introduce ODRL, first benchmark tailored for evaluating RL methods. ODRL contains four experimental settings source and target can be either online or offline, provides diverse tasks broad spectrum shifts, making it...
How to make use of multicore computing resources accelerate the block cryptography applications has become a common concern problem. And have not yet been explored in procedure level speculation thoroughly. This paper proposes mechanism for accelerating applications, including execution model, synchronization strategy and analysis method, etc. It also takes RC5 AES examples analyze their potential speedups memory accessing characteristics. The experimental results show that: (1) speculation,...